Verified75% confidenceFactExact time
The probability of hallucination increases significantly when contradictory information exists in the training data or when the model is asked about domains that are sparsely represented in the training data.
3
Sources
75%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
热爱LLM却厌恶炒作：工程师如何理性看待大语言模型
Related Claims
VerifiedLarge models output the most likely next word rather than precise retrieval of facts, which leads to hallucinations in domains with sparse coverage in the training data.83% similarVerifiedThe three main causes of hallucinations in large models are training data noise, the probability-first mechanism, and insufficient data timeliness.82% similarUnverifiedEpistemic uncertainty stems from insufficient training data and can be reduced by adding more data, while aleatoric uncertainty stems from inherent noise in the data and cannot be eliminated by adding more data.78% similarUnverifiedLLM agents often share similar training data, similar prior biases, and similar hallucination tendencies, causing their errors to be highly correlated.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/504034API
curl https://kongchang.com/api/v1/knowledge/claims/504034MCP
get_claim(id=504034)